The Seventh ISCA Tutorial and Research Workshop on Speech Synthesis

Kyoto, Japan
September 22-24, 2010

HMM-Based Polyglot Speech Synthesis by Speaker and Language Adaptive Training

Heiga Zen, Norbert Braunschweiler, Sabine Buchholz, Kate Knill, Sacha Krstulovic, Javier Latorre

Toshiba Research Europe Ltd., Cambridge Research Laboratory, Cambridge, UK

This paper describes a technique for speaker and language adaptive training (SLAT) for HMM-based polyglot speech synthesis and its evaluations on a multi-lingual speech corpus. The SLAT technique allows multi-speaker/multi-language adaptive training and synthesis to be performed. Experimental results show that the SLAT technique achieves better naturalness than both speaker-adaptively trained language-dependent (LD-SAT) and language-independent (LI-SAT) models. In cross-lingual adaptation speaker similarity tests SLAT and LI-SAT outperform LD-SAT but there are still significant differences between polyglot adaptation and intra-language adaptation.

Full Paper

Bibliographic reference.  Zen, Heiga / Braunschweiler, Norbert / Buchholz, Sabine / Knill, Kate / Krstulovic, Sacha / Latorre, Javier (2010): "HMM-based polyglot speech synthesis by speaker and language adaptive training", In SSW7-2010, 186-191.